Performance of machine learning methods in predicting water quality index based on irregular data set: application on Illizi region (Algerian southeast)

Applied Water Science, Journal Year: 2021, Volume and Issue: 11(12)

Published: Nov. 6, 2021

Abstract Groundwater quality appraisal is one of the most crucial tasks to ensure safe drinking water sources. Concurrently, a index (WQI) requires some parameters. Conventionally, WQI computation consumes time and often found with various errors during subindex calculation. To this end, 8 artificial intelligence algorithms, e.g., multilinear regression (MLR), random forest (RF), M5P tree (M5P), subspace (RSS), additive (AR), neural network (ANN), support vector (SVR), locally weighted linear (LWLR), were employed generate prediction in Illizi region, southeast Algeria. Using best subset regression, 12 different input combinations developed strategy work was based on two scenarios. The first scenario aims reduce consumption computation, where all parameters used as inputs. second intends show variation critical cases when necessary analyses are unavailable, whereas inputs reduced sensitivity analysis. models appraised using several statistical metrics including correlation coefficient (R), mean absolute error (MAE), root square (RMSE), relative (RAE), (RRSE). results reveal that TDS TH key drivers influencing study area. comparison performance evaluation metric shows MLR model has higher accuracy compared other terms 1, 1.4572*10–08, 2.1418*10–08, 1.2573*10–10%, 3.1708*10–08% for R, MAE, RMSE, RAE, RRSE, respectively. executed less rate by RF 0.9984, 1.9942, 3.2488, 4.693, 5.9642 outcomes paper would be interest planners improving sustainable management plans groundwater resources.

Language: Английский

---

Application of machine learning in groundwater quality modeling - A comprehensive review

Water Research, Journal Year: 2023, Volume and Issue: 233, P. 119745 - 119745

Published: Feb. 16, 2023

Language: Английский

---

Prediction of irrigation groundwater quality parameters using ANN, LSTM, and MLR models

Environmental Science and Pollution Research, Journal Year: 2021, Volume and Issue: 29(14), P. 21067 - 21091

Published: Nov. 8, 2021

Language: Английский

---

Prediction of Sodium Hazard of Irrigation Purpose using Artificial Neural Network Modelling

Sustainability, Journal Year: 2023, Volume and Issue: 15(9), P. 7593 - 7593

Published: May 5, 2023

The present study was carried out using artificial neural network (ANN) model for predicting the sodium hazardness, i.e., adsorption ratio (SAR), percent (%Na) residual, Kelly’s (KR), and residual carbonate (RSC) in groundwater of Pratapgarh district Southern Rajasthan, India. This focuses on verifying suitability water irrigational purpose, wherein more decline coupled with quality problems compared to other areas are observed. southern part Rajasthan State is populated as rest parts. which leads industrialization, urbanization, evolutionary changes agricultural production region. Therefore, it necessary propose innovative methods analyzing (WQ) use. aims develop an optimized predict hazardness irrigation purposes. ANN developed ‘nntool’ MATLAB software. trained validated ten years (2010–2020) data. An L-M 3-layer back propagation technique adopted architecture a reliable accurate irrigation. Furthermore, statistical performance indicators, such RMSE, IA, R, MBE, were used check consistency prediction results. model, ANN4 (3-12-1), (4-15-1), ANN1 (4-5-1), found best suited SAR, %Na, RSC, KR indicators district. analysis (3-12-1) led correlation coefficient = 1, IA RMS 0.14, MBE 0.0050. Hence, proposed provides satisfactory match empirically generated datasets observed wells. development modeling may help useful planning sustainable management resources crop plans per quality.

Language: Английский

---

Water quality prediction using machine learning models based on grid search method

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(12), P. 35307 - 35334

Published: Sept. 29, 2023

Abstract Water quality is very dominant for humans, animals, plants, industries, and the environment. In last decades, of water has been impacted by contamination pollution. this paper, challenge to anticipate Quality Index (WQI) Classification (WQC), such that WQI a vital indicator validity. study, parameters optimization tuning are utilized improve accuracy several machine learning models, where techniques process predicting WQC. Grid search method used optimizing four classification models also, regression models. Random forest (RF) model, Extreme Gradient Boosting (Xgboost) (GB) Adaptive (AdaBoost) model as K-nearest neighbor (KNN) regressor decision tree (DT) support vector (SVR) multi-layer perceptron (MLP) WQI. addition, preprocessing step including, data imputation (mean imputation) normalization were performed fit make it convenient any further processing. The dataset in study includes 7 features 1991 instances. To examine efficacy approaches, five assessment metrics computed: accuracy, recall, precision, Matthews's Correlation Coefficient (MCC), F1 score. assess effectiveness Mean Absolute Error (MAE), Median (MedAE), Square (MSE), coefficient determination (R 2 ). terms classification, testing findings showed GB produced best results, with an 99.50% when WQC values. According experimental MLP outperformed other achieved R value 99.8% while

Language: Английский

---

Hydro-chemical assessment of fluoride and nitrate in groundwater from east and west coasts of Bangladesh and India

Journal of Cleaner Production, Journal Year: 2022, Volume and Issue: 372, P. 133675 - 133675

Published: Aug. 24, 2022

Language: Английский

---

An Integrated Statistical-Machine Learning Approach for Runoff Prediction

Sustainability, Journal Year: 2022, Volume and Issue: 14(13), P. 8209 - 8209

Published: July 5, 2022

Nowadays, great attention has been attributed to the study of runoff and its fluctuation over space time. There is a crucial need for good soil water management system overcome challenges scarcity other natural adverse events like floods landslides, among others. Rainfall–runoff (R-R) modeling an appropriate approach prediction, making it possible take preventive measures avoid damage caused by hazards such as floods. In present study, several data-driven models, namely, multiple linear regression (MLR), adaptive splines (MARS), support vector machine (SVM), random forest (RF), were used rainfall–runoff prediction Gola watershed, located in south-eastern part Uttarakhand. The model analysis was conducted using daily rainfall data 12 years (2009 2020) watershed. first 80% complete train model, remaining 20% testing period. performance models evaluated based on coefficient determination (R2), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), percent bias (PBAIS) indices. addition numerical comparison, evaluated. Their performances graphical plotting, i.e., time-series line diagram, scatter plot, violin relative Taylor diagram (TD). comparison results revealed that four heuristic methods gave higher accuracy than MLR model. Among learning RF (RMSE (m3/s), R2, NSE, PBIAS (%) = 6.31, 0.96, 0.94, −0.20 during training period, respectively, 5.53, 0.95, 0.92, respectively) surpassed MARS, SVM, forecasting all cases studied. outperformed models’ periods. It can be summarized best-in-class delivers strong potential

Language: Английский

---

Assessment of PTEs in water resources by integrating HHRISK code, water quality indices, multivariate statistics, and ANNs

Geocarto International, Journal Year: 2022, Volume and Issue: 37(25), P. 10407 - 10433

Published: Jan. 26, 2022

The use of contaminated water for drinking and sanitary purposes can be detrimental to human health. In this article, the Human Health Risk (HHRISK) code was applied, alongside modified heavy metal index (MHMI), synthetic pollution (SPI), entropy-weighted quality (EWQI), investigate status, ingestion, dermal health risks potentially toxic elements (PTEs) (Fe, Zn, Mn, Pb, Cr, Ni) in resources from Umunya area, Nigeria. Physicochemical measurements followed standard methods. Results MHMI, SPI, EWQI revealed that about 60% samples had low were considered suitable consumption, while 40% unsuitable. Further, cumulative non-carcinogenic risk scores indicated pose low-medium high child adult populations. Contrarily, results carcinogenic showed 6.67% expose users risks, whereas 93.33% them risks. Although there are agreements between both populations (regarding risks), it is worth highlighting children higher. Therefore, study area more vulnerable Also, due ingestion higher than contact. Linear regression analysis strong agreement indexical models While artificial neural networks multiple linear accurately predicted indices, hierarchical dendrograms efficiently classed into various spatiotemporal groups.

Language: Английский

---

A comprehensive review on water pollution, South Asia Region: Pakistan

Urban Climate, Journal Year: 2023, Volume and Issue: 48, P. 101413 - 101413

Published: Jan. 25, 2023

Language: Английский

---

Predicting lake water quality index with sensitivity-uncertainty analysis using deep learning algorithms

Journal of Cleaner Production, Journal Year: 2023, Volume and Issue: 406, P. 136885 - 136885

Published: April 3, 2023

Language: Английский

---